Loading ...
Sorry, an error occurred while loading the content.

Suppressing Sensitive Info From Free Text

Expand Messages
  • Will Ross
    I m looking for a tool to suppress sensitive information (e.g., HIV status, etc.) from free text clinical notes prior to allowing the notes to be published
    Message 1 of 19 , Mar 2, 2007
    • 0 Attachment
      I'm looking for a tool to suppress sensitive information (e.g., HIV
      status, etc.) from free text clinical notes prior to allowing the
      notes to be published from a protected, physician-only area into
      general circulation patient records for the clinic. What existing
      FOSS solutions are available?

      With best regards,

      [wr]

      - - - - - - - -

      will ross
      chief information officer
      mendocino health records exchange
      216 west perkins street, suite 206
      ukiah, california 95482 usa
      707.462.6369 [office]
      707.462.5015 [fax]
      www.mendocinohre.org

      - - - - - - - -

      "Getting people to adopt common standards is impeded by patents."
      Sir Tim Berners-Lee, BCS, 2006

      - - - - - - - -
    • Maury Pepper
      1. How good does it have to be? Is 5% leakage of sensitive information OK? 2. Another view: ALL of the information is sensitive . 3. Another
      Message 2 of 19 , Mar 2, 2007
      • 0 Attachment
        <can-of-worms>
        1. How good does it have to be? Is 5% leakage of "sensitive information" OK?
        2. Another view: ALL of the information is "sensitive".
        3. Another view: The patient MUST have input as to who can see what.
        </can-of-worms>



        ----- Original Message -----
        From: Will Ross
        To: openhealth@yahoogroups.com
        Sent: Friday, March 02, 2007 10:58 AM
        Subject: [openhealth] Suppressing Sensitive Info From Free Text


        I'm looking for a tool to suppress sensitive information (e.g., HIV
        status, etc.) from free text clinical notes prior to allowing the
        notes to be published from a protected, physician-only area into
        general circulation patient records for the clinic. What existing
        FOSS solutions are available?

        With best regards,

        [wr]

        - - - - - - - -

        will ross
        chief information officer
        mendocino health records exchange
        216 west perkins street, suite 206
        ukiah, california 95482 usa
        707.462.6369 [office]
        707.462.5015 [fax]
        www.mendocinohre.org

        - - - - - - - -

        "Getting people to adopt common standards is impeded by patents."
        Sir Tim Berners-Lee, BCS, 2006

        - - - - - - - -





        [Non-text portions of this message have been removed]
      • Fred Trotter
        Will, I am confused too. Wouldnt such a technology have to be turning test capable? Are you looking for something that can search Free Text make a
        Message 3 of 19 , Mar 2, 2007
        • 0 Attachment
          Will,
          I am confused too. Wouldnt such a technology have to be turning
          test capable? Are you looking for something that can search Free Text make a
          determination if it is related to HIV, and then catagorize the whole text as
          "related to HIV"? Or are you looking for something that is capable of
          allowing the rest of the note to pass through, and only eliminate the
          portions relating to HIV. (which seems much harder).

          Could you give an example of how your application might work?

          -FT

          On 3/2/07, Will Ross <wross@...> wrote:
          >
          > I'm looking for a tool to suppress sensitive information (e.g., HIV
          > status, etc.) from free text clinical notes prior to allowing the
          > notes to be published from a protected, physician-only area into
          > general circulation patient records for the clinic. What existing
          > FOSS solutions are available?
          >
          > With best regards,
          >
          > [wr]
          >
          > - - - - - - - -
          >
          > will ross
          > chief information officer
          > mendocino health records exchange
          > 216 west perkins street, suite 206
          > ukiah, california 95482 usa
          > 707.462.6369 [office]
          > 707.462.5015 [fax]
          > www.mendocinohre.org
          >
          > - - - - - - - -
          >
          > "Getting people to adopt common standards is impeded by patents."
          > Sir Tim Berners-Lee, BCS, 2006
          >
          > - - - - - - - -
          >
          >
          >
          >
          >
          >
          > Yahoo! Groups Links
          >
          >
          >
          >


          --
          Fred Trotter
          http://www.fredtrotter.com


          [Non-text portions of this message have been removed]
        • Stuart Turner
          ... Will: In general, this falls under a number of natural language processing tools and specific steps toward tokenizing, chunking, part-of-speech tagging,
          Message 4 of 19 , Mar 2, 2007
          • 0 Attachment
            On 3/2/07, Will Ross <wross@...> wrote:
            > I'm looking for a tool to suppress sensitive information (e.g., HIV
            > status, etc.) from free text clinical notes

            Will:

            In general, this falls under a number of natural language processing
            tools and specific steps toward tokenizing, chunking, part-of-speech
            tagging, classifying (e.g. to vocabularies or concept identifiers),
            matching, anonymizing/de-identifying, etc.

            The two tools I've worked with a little in the past are:

            1) GATE - General Architecture for Text Engineering, developed at the
            University of Sheffield NLP group in the UK
            http://gate.ac.uk/

            2) Project DIAsDEM and the DIAsDEM workbench developed by a great
            group, including Karsten Winkler, in Germany
            http://wwwiti.cs.uni-magdeburg.de/~graubitz/diasdem/

            These more are less are a suite of tools containing a number of
            individual components to perform the various NLP tasks, in some
            sequence (steps can be recorded and set as a macro or batch) and with
            customization for using language specific knowledge bases (e.g. names
            derived from a US Census database) or UMLS concept identifiers.

            A couple of example projects using these kinds of tools is the caTIES
            application (http://caties.cabig.upmc.edu/index.html) for extraction
            and classification of free text pathology reports and the RODS
            biosurveillance application, also from the Univ of Pittsburgh
            (http://openrods.sourceforge.net/), that takes free text and ICD-9
            data for syndromic classification.

            A specific NLP approach to HIV/AIDS notes performed at Columbia is
            here (the MedLEE or "Medical Language Processing"):
            http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=1480114

            ~ Stuart

            --
            Dr. Stuart Turner
            Health Informatics Graduate Program and
            Biomedical Informatics Research & Consulting Service
            University of California Davis Health System
            http://www.ucdmc.ucdavis.edu/informatics
            http://www.ucdmc.ucdavis.edu/bircs

            UCDHS-ASB
            2450 48th St, Suite 2685
            Sacramento, CA 95817
            916.734.3857 (voice) | 916.734.3975 (fax)
            916.873.4325 (cell) | stuart.turner.ucdavis (Skype)
          • David Forslund
            Agreed. Such an action would at least have to have approval of a local HIPAA board. How would one prove it is reliable at removing protected information? If
            Message 5 of 19 , Mar 2, 2007
            • 0 Attachment
              Agreed. Such an action would at least have to have approval of a local
              HIPAA board.
              How would one "prove" it is reliable at removing protected information?
              If it is
              an algorithm, the algorithm would need local approval.

              Dave
              Maury Pepper wrote:
              > <can-of-worms>
              > 1. How good does it have to be? Is 5% leakage of "sensitive information" OK?
              > 2. Another view: ALL of the information is "sensitive".
              > 3. Another view: The patient MUST have input as to who can see what.
              > </can-of-worms>
              >
              >
              >
              > ----- Original Message -----
              > From: Will Ross
              > To: openhealth@yahoogroups.com
              > Sent: Friday, March 02, 2007 10:58 AM
              > Subject: [openhealth] Suppressing Sensitive Info From Free Text
              >
              >
              > I'm looking for a tool to suppress sensitive information (e.g., HIV
              > status, etc.) from free text clinical notes prior to allowing the
              > notes to be published from a protected, physician-only area into
              > general circulation patient records for the clinic. What existing
              > FOSS solutions are available?
              >
              > With best regards,
              >
              > [wr]
              >
              > - - - - - - - -
              >
              > will ross
              > chief information officer
              > mendocino health records exchange
              > 216 west perkins street, suite 206
              > ukiah, california 95482 usa
              > 707.462.6369 [office]
              > 707.462.5015 [fax]
              > www.mendocinohre.org
              >
              > - - - - - - - -
              >
              > "Getting people to adopt common standards is impeded by patents."
              > Sir Tim Berners-Lee, BCS, 2006
              >
              > - - - - - - - -
              >
              >
            • 80n
              Will The only acceptable answer would be Maury s option 3. The patient decides. Anything else would be be inappropriate. And not just HIV status. The
              Message 6 of 19 , Mar 2, 2007
              • 0 Attachment
                Will
                The only acceptable answer would be Maury's option 3. The patient decides.
                Anything else would be be inappropriate.

                And not just HIV status. The patient, and only the patient, should have the
                right to determine who has access to anything that the patient might
                consider sensitive. And only the patient can determine what is or is not
                sensitive.

                80n



                On 3/2/07, Will Ross <wross@...> wrote:
                >
                > I'm looking for a tool to suppress sensitive information (e.g., HIV
                > status, etc.) from free text clinical notes prior to allowing the
                > notes to be published from a protected, physician-only area into
                > general circulation patient records for the clinic. What existing
                > FOSS solutions are available?
                >
                > With best regards,
                >
                > [wr]
                >
                > - - - - - - - -
                >
                > will ross
                > chief information officer
                > mendocino health records exchange
                > 216 west perkins street, suite 206
                > ukiah, california 95482 usa
                > 707.462.6369 [office]
                > 707.462.5015 [fax]
                > www.mendocinohre.org
                >
                > - - - - - - - -
                >
                > "Getting people to adopt common standards is impeded by patents."
                > Sir Tim Berners-Lee, BCS, 2006
                >
                > - - - - - - - -
                >
                >
                >


                [Non-text portions of this message have been removed]
              • Will Ross
                Dear 80n, This is, in fact, the use case in discussion. Assume the patient has agreed to suppress detail x from circulation beyond his/her physician s eyes
                Message 7 of 19 , Mar 2, 2007
                • 0 Attachment
                  Dear 80n,

                  This is, in fact, the use case in discussion.

                  Assume the patient has agreed to suppress "detail x" from circulation
                  beyond his/her physician's eyes in the local free text based records
                  system. What are the best FOSS tools to publish to the general
                  circulation records environment a correctly edited version of a text
                  file?

                  With best regards,

                  [wr]

                  - - - - - - - -

                  On Mar 2, 2007, at 4:08 PM, 80n wrote:

                  > Will
                  > The only acceptable answer would be Maury's option 3. The patient
                  > decides.
                  > Anything else would be be inappropriate.
                  >
                  > And not just HIV status. The patient, and only the patient, should
                  > have the
                  > right to determine who has access to anything that the patient might
                  > consider sensitive. And only the patient can determine what is or
                  > is not
                  > sensitive.
                  >
                  > 80n
                  >
                  >
                  >
                  > On 3/2/07, Will Ross <wross@...> wrote:
                  >>
                  >> I'm looking for a tool to suppress sensitive information (e.g., HIV
                  >> status, etc.) from free text clinical notes prior to allowing the
                  >> notes to be published from a protected, physician-only area into
                  >> general circulation patient records for the clinic. What existing
                  >> FOSS solutions are available?
                  >>
                  >> With best regards,
                  >>
                  >> [wr]
                  >>
                  >> - - - - - - - -
                  >>
                  >> will ross
                  >> chief information officer
                  >> mendocino health records exchange
                  >> 216 west perkins street, suite 206
                  >> ukiah, california 95482 usa
                  >> 707.462.6369 [office]
                  >> 707.462.5015 [fax]
                  >> www.mendocinohre.org
                  >>
                  >> - - - - - - - -
                  >>
                  >> "Getting people to adopt common standards is impeded by patents."
                  >> Sir Tim Berners-Lee, BCS, 2006
                  >>
                  >> - - - - - - - -
                  >>
                  >>
                  >>
                  >
                  >
                  > [Non-text portions of this message have been removed]
                  >
                  >
                  >
                  > ------------------------ Yahoo! Groups Sponsor --------------------
                  > ~-->
                  > Yahoo! Groups gets a make over. See the new email design.
                  > http://us.click.yahoo.com/hOt0.A/lOaOAA/yQLSAA/W4wwlB/TM
                  > --------------------------------------------------------------------
                  > ~->
                  >
                  >
                  > Yahoo! Groups Links
                  >
                  >
                  >
                  >

                  [wr]

                  - - - - - - - -

                  will ross
                  chief information officer
                  mendocino health records exchange
                  216 west perkins street, suite 206
                  ukiah, california 95482 usa
                  707.462.6369 [office]
                  707.462.5015 [fax]
                  www.mendocinohre.org

                  - - - - - - - -

                  "Getting people to adopt common standards is impeded by patents."
                  Sir Tim Berners-Lee, BCS, 2006

                  - - - - - - - -
                • David Forslund
                  That is the reason for the patient consent in the HIPAA regulations. In my opinion, the patient would need to review the data to approve its release. The
                  Message 8 of 19 , Mar 2, 2007
                  • 0 Attachment
                    That is the reason for the patient consent in the HIPAA regulations. In
                    my opinion, the
                    patient would need to review the data to approve its release. The usual
                    escape clause
                    is for the data to be used in the normal care of the patient But if it
                    is for some
                    other purpose, then it needs specific patient consent. But a local
                    HIPAA board
                    should be able to provide more precise guidance. The general accurate
                    suppression
                    of sensitive information would seem to me to be impossible.

                    Dave
                    80n wrote:
                    > Will
                    > The only acceptable answer would be Maury's option 3. The patient decides.
                    > Anything else would be be inappropriate.
                    >
                    > And not just HIV status. The patient, and only the patient, should have the
                    > right to determine who has access to anything that the patient might
                    > consider sensitive. And only the patient can determine what is or is not
                    > sensitive.
                    >
                    > 80n
                    >
                    >
                    >
                    > On 3/2/07, Will Ross <wross@...> wrote:
                    >
                    >> I'm looking for a tool to suppress sensitive information (e.g., HIV
                    >> status, etc.) from free text clinical notes prior to allowing the
                    >> notes to be published from a protected, physician-only area into
                    >> general circulation patient records for the clinic. What existing
                    >> FOSS solutions are available?
                    >>
                    >> With best regards,
                    >>
                    >> [wr]
                    >>
                    >> - - - - - - - -
                    >>
                    >> will ross
                    >> chief information officer
                    >> mendocino health records exchange
                    >> 216 west perkins street, suite 206
                    >> ukiah, california 95482 usa
                    >> 707.462.6369 [office]
                    >> 707.462.5015 [fax]
                    >> www.mendocinohre.org
                    >>
                    >> - - - - - - - -
                    >>
                    >> "Getting people to adopt common standards is impeded by patents."
                    >> Sir Tim Berners-Lee, BCS, 2006
                    >>
                    >> - - - - - - - -
                    >>
                    >>
                    >>
                    >>
                    >
                    >
                  • Nandalal Gunaratne
                    Will, It is not a good idea to have sensitive information in free text. If you do, it should not go to general circulation , right? How can one extract such
                    Message 9 of 19 , Mar 3, 2007
                    • 0 Attachment
                      Will,

                      It is not a good idea to have sensitive information in
                      free text. If you do, it should not go to "general
                      circulation", right?

                      How can one extract such info from free text? One way
                      is to remove such words from free text files using a
                      macro of some sort. "FInd and replace" can be used to
                      remove words like HIV with a blank?

                      There cannot be an automated solution to this, unless
                      it is cutting edge! ( ..or so we like to think to
                      cover our ignorance!)

                      I wonder if we have adequate knowledge as to what
                      constitutes "sensitive information" to patients. A
                      good study is needed....


                      Nandalal




                      --- Fred Trotter <fred.trotter@...> wrote:

                      > Will,
                      > I am confused too. Wouldnt such a
                      > technology have to be turning
                      > test capable? Are you looking for something that can
                      > search Free Text make a
                      > determination if it is related to HIV, and then
                      > catagorize the whole text as
                      > "related to HIV"? Or are you looking for something
                      > that is capable of
                      > allowing the rest of the note to pass through, and
                      > only eliminate the
                      > portions relating to HIV. (which seems much harder).
                      >
                      > Could you give an example of how your application
                      > might work?
                      >
                      > -FT
                      >
                      > On 3/2/07, Will Ross <wross@...> wrote:
                      > >
                      > > I'm looking for a tool to suppress sensitive
                      > information (e.g., HIV
                      > > status, etc.) from free text clinical notes prior
                      > to allowing the
                      > > notes to be published from a protected,
                      > physician-only area into
                      > > general circulation patient records for the
                      > clinic. What existing
                      > > FOSS solutions are available?
                      > >
                      > > With best regards,
                      > >
                      > > [wr]
                      > >
                      > > - - - - - - - -
                      > >
                      > > will ross
                      > > chief information officer
                      > > mendocino health records exchange
                      > > 216 west perkins street, suite 206
                      > > ukiah, california 95482 usa
                      > > 707.462.6369 [office]
                      > > 707.462.5015 [fax]
                      > > www.mendocinohre.org
                      > >
                      > > - - - - - - - -
                      > >
                      > > "Getting people to adopt common standards is
                      > impeded by patents."
                      > > Sir Tim Berners-Lee, BCS, 2006
                      > >
                      > > - - - - - - - -
                      > >
                      > >
                      > >
                      > >
                      > >
                      > >
                      > > Yahoo! Groups Links
                      > >
                      > >
                      > >
                      > >
                      >
                      >
                      > --
                      > Fred Trotter
                      > http://www.fredtrotter.com
                      >
                      >
                      > [Non-text portions of this message have been
                      > removed]
                      >
                      >




                      ____________________________________________________________________________________
                      It's here! Your new message!
                      Get new email alerts with the free Yahoo! Toolbar.
                      http://tools.search.yahoo.com/toolbar/features/mail/
                    • Nandalal Gunaratne
                      Thanks Ross! Due to your question i have come to know the present state of text mining and NLP. These will give you your solution I guess.
                      Message 10 of 19 , Mar 3, 2007
                      • 0 Attachment
                        Thanks Ross!

                        Due to your question i have come to know the present
                        state of text mining and NLP. These will give you your
                        solution I guess.

                        http://portal.acm.org/citation.cfm?id=1089824&dl=acm&coll=&CFID=15151515&CFTOKEN=6184618

                        nandalal
                        --- Will Ross <wross@...> wrote:

                        > Dear 80n,
                        >
                        > This is, in fact, the use case in discussion.
                        >
                        > Assume the patient has agreed to suppress "detail x"
                        > from circulation
                        > beyond his/her physician's eyes in the local free
                        > text based records
                        > system. What are the best FOSS tools to publish to
                        > the general
                        > circulation records environment a correctly edited
                        > version of a text
                        > file?
                        >
                        > With best regards,
                        >
                        > [wr]
                        >
                        > - - - - - - - -
                        >
                        > On Mar 2, 2007, at 4:08 PM, 80n wrote:
                        >
                        > > Will
                        > > The only acceptable answer would be Maury's option
                        > 3. The patient
                        > > decides.
                        > > Anything else would be be inappropriate.
                        > >
                        > > And not just HIV status. The patient, and only
                        > the patient, should
                        > > have the
                        > > right to determine who has access to anything that
                        > the patient might
                        > > consider sensitive. And only the patient can
                        > determine what is or
                        > > is not
                        > > sensitive.
                        > >
                        > > 80n
                        > >
                        > >
                        > >
                        > > On 3/2/07, Will Ross <wross@...>
                        > wrote:
                        > >>
                        > >> I'm looking for a tool to suppress sensitive
                        > information (e.g., HIV
                        > >> status, etc.) from free text clinical notes prior
                        > to allowing the
                        > >> notes to be published from a protected,
                        > physician-only area into
                        > >> general circulation patient records for the
                        > clinic. What existing
                        > >> FOSS solutions are available?
                        > >>
                        > >> With best regards,
                        > >>
                        > >> [wr]
                        > >>
                        > >> - - - - - - - -
                        > >>
                        > >> will ross
                        > >> chief information officer
                        > >> mendocino health records exchange
                        > >> 216 west perkins street, suite 206
                        > >> ukiah, california 95482 usa
                        > >> 707.462.6369 [office]
                        > >> 707.462.5015 [fax]
                        > >> www.mendocinohre.org
                        > >>
                        > >> - - - - - - - -
                        > >>
                        > >> "Getting people to adopt common standards is
                        > impeded by patents."
                        > >> Sir Tim Berners-Lee, BCS, 2006
                        > >>
                        > >> - - - - - - - -
                        > >>
                        > >>
                        > >>
                        > >
                        > >
                        > > [Non-text portions of this message have been
                        > removed]
                        > >
                        > >
                        > >
                        > > ------------------------ Yahoo! Groups Sponsor
                        > --------------------
                        > > ~-->
                        > > Yahoo! Groups gets a make over. See the new email
                        > design.
                        > >
                        >
                        http://us.click.yahoo.com/hOt0.A/lOaOAA/yQLSAA/W4wwlB/TM
                        > >
                        >
                        --------------------------------------------------------------------
                        >
                        > > ~->
                        > >
                        > >
                        > > Yahoo! Groups Links
                        > >
                        > >
                        > >
                        > >
                        >
                        > [wr]
                        >
                        > - - - - - - - -
                        >
                        > will ross
                        > chief information officer
                        > mendocino health records exchange
                        > 216 west perkins street, suite 206
                        > ukiah, california 95482 usa
                        > 707.462.6369 [office]
                        > 707.462.5015 [fax]
                        > www.mendocinohre.org
                        >
                        > - - - - - - - -
                        >
                        > "Getting people to adopt common standards is impeded
                        > by patents."
                        > Sir Tim Berners-Lee, BCS, 2006
                        >
                        > - - - - - - - -
                        >
                        >
                        >




                        ____________________________________________________________________________________
                        The fish are biting.
                        Get more visitors on your site using Yahoo! Search Marketing.
                        http://searchmarketing.yahoo.com/arp/sponsoredsearch_v2.php
                      • Adrian Midgley
                        ... As automation ... I think this is regarded everywhere as a hard problem. In the UK I believe it would be generally regarded as if not actually impossible,
                        Message 11 of 19 , Mar 3, 2007
                        • 0 Attachment
                          Will Ross wrote:
                          >
                          > I'm looking for a tool to suppress sensitive information (e.g., HIV
                          > status, etc.) from free text clinical notes prior to allowing the
                          > notes to be published from a protected, physician-only area into
                          > general circulation patient records for the clinic. What existing
                          > FOSS solutions are available?
                          >











                          As automation ...
                          I think this is regarded everywhere as a hard problem.

                          In the UK I believe it would be generally regarded as if not actually
                          impossible, at least unfeasibly hard by a very large margin.


                          As semi-automation, presenting line after line to a human, and offering
                          hints I suppose there is scope.


                          If HIV status is held as a code or information in a field, then this
                          would just be a reporting problem, but one can't rely on it not being
                          repeated in the free text, clinical info echoed back in lab results etc.

                          Difficult.


                          On the question of patients and confidentiality, the (Ross) Anderson
                          Guidelines as published in the BMJ some years ago are probably good.

                          --
                          A
                        • David Forslund
                          If one uses a structured report along the lines of the ASTM CCR, then I think it would be relatively easy to remove the sensitive information, since all of
                          Message 12 of 19 , Mar 3, 2007
                          • 0 Attachment
                            If one uses a structured report along the lines of the ASTM CCR, then
                            I think it would be "relatively" easy to remove the sensitive information,
                            since all of the data would be tagged.

                            Dave
                            Nandalal Gunaratne wrote:
                            > Will,
                            >
                            > It is not a good idea to have sensitive information in
                            > free text. If you do, it should not go to "general
                            > circulation", right?
                            >
                            > How can one extract such info from free text? One way
                            > is to remove such words from free text files using a
                            > macro of some sort. "FInd and replace" can be used to
                            > remove words like HIV with a blank?
                            >
                            > There cannot be an automated solution to this, unless
                            > it is cutting edge! ( ..or so we like to think to
                            > cover our ignorance!)
                            >
                            > I wonder if we have adequate knowledge as to what
                            > constitutes "sensitive information" to patients. A
                            > good study is needed....
                            >
                            >
                            > Nandalal
                            >
                            >
                            >
                            >
                            > --- Fred Trotter <fred.trotter@...> wrote:
                            >
                            >
                            >> Will,
                            >> I am confused too. Wouldnt such a
                            >> technology have to be turning
                            >> test capable? Are you looking for something that can
                            >> search Free Text make a
                            >> determination if it is related to HIV, and then
                            >> catagorize the whole text as
                            >> "related to HIV"? Or are you looking for something
                            >> that is capable of
                            >> allowing the rest of the note to pass through, and
                            >> only eliminate the
                            >> portions relating to HIV. (which seems much harder).
                            >>
                            >> Could you give an example of how your application
                            >> might work?
                            >>
                            >> -FT
                            >>
                            >> On 3/2/07, Will Ross <wross@...> wrote:
                            >>
                            >>> I'm looking for a tool to suppress sensitive
                            >>>
                            >> information (e.g., HIV
                            >>
                            >>> status, etc.) from free text clinical notes prior
                            >>>
                            >> to allowing the
                            >>
                            >>> notes to be published from a protected,
                            >>>
                            >> physician-only area into
                            >>
                            >>> general circulation patient records for the
                            >>>
                            >> clinic. What existing
                            >>
                            >>> FOSS solutions are available?
                            >>>
                            >>> With best regards,
                            >>>
                            >>> [wr]
                            >>>
                            >>> - - - - - - - -
                            >>>
                            >>> will ross
                            >>> chief information officer
                            >>> mendocino health records exchange
                            >>> 216 west perkins street, suite 206
                            >>> ukiah, california 95482 usa
                            >>> 707.462.6369 [office]
                            >>> 707.462.5015 [fax]
                            >>> www.mendocinohre.org
                            >>>
                            >>> - - - - - - - -
                            >>>
                            >>> "Getting people to adopt common standards is
                            >>>
                            >> impeded by patents."
                            >>
                            >>> Sir Tim Berners-Lee, BCS, 2006
                            >>>
                            >>> - - - - - - - -
                            >>>
                            >>>
                            >>>
                            >>>
                            >>>
                            >>>
                            >>> Yahoo! Groups Links
                            >>>
                            >>>
                            >>>
                            >>>
                            >>>
                            >> --
                            >> Fred Trotter
                            >> http://www.fredtrotter.com
                            >>
                            >>
                            >>
                            >
                          • Will Ross
                            Nandalal, I believe you are exactly right. In the case of this interesting problem the key issue is to identify the appropriate middleware services to safely
                            Message 13 of 19 , Mar 3, 2007
                            • 0 Attachment
                              Nandalal,

                              I believe you are exactly right. In the case of this interesting
                              problem the key issue is to identify the appropriate middleware
                              services to safely expose legacy patient data. This is a different
                              problem from the opportunity to create structured and coded data as
                              new systems with rich onboard permissions and are brought on line.

                              With best regards,

                              [wr]

                              - - - - - - - -

                              On Mar 3, 2007, at 2:02 AM, Nandalal Gunaratne wrote:

                              > Thanks Ross!
                              >
                              > Due to your question i have come to know the present
                              > state of text mining and NLP. These will give you your
                              > solution I guess.
                              >
                              > http://portal.acm.org/citation.cfm?
                              > id=1089824&dl=acm&coll=&CFID=15151515&CFTOKEN=6184618
                              >
                              > nandalal
                              > --- Will Ross <wross@...> wrote:
                              >
                              >> Dear 80n,
                              >>
                              >> This is, in fact, the use case in discussion.
                              >>
                              >> Assume the patient has agreed to suppress "detail x"
                              >> from circulation
                              >> beyond his/her physician's eyes in the local free
                              >> text based records
                              >> system. What are the best FOSS tools to publish to
                              >> the general
                              >> circulation records environment a correctly edited
                              >> version of a text
                              >> file?
                              >>
                              >> With best regards,
                              >>
                              >> [wr]
                              >>
                              >> - - - - - - - -
                              >>
                              >> On Mar 2, 2007, at 4:08 PM, 80n wrote:
                              >>
                              >>> Will
                              >>> The only acceptable answer would be Maury's option
                              >> 3. The patient
                              >>> decides.
                              >>> Anything else would be be inappropriate.
                              >>>
                              >>> And not just HIV status. The patient, and only
                              >> the patient, should
                              >>> have the
                              >>> right to determine who has access to anything that
                              >> the patient might
                              >>> consider sensitive. And only the patient can
                              >> determine what is or
                              >>> is not
                              >>> sensitive.
                              >>>
                              >>> 80n
                              >>>
                              >>>
                              >>>
                              >>> On 3/2/07, Will Ross <wross@...>
                              >> wrote:
                              >>>>
                              >>>> I'm looking for a tool to suppress sensitive
                              >> information (e.g., HIV
                              >>>> status, etc.) from free text clinical notes prior
                              >> to allowing the
                              >>>> notes to be published from a protected,
                              >> physician-only area into
                              >>>> general circulation patient records for the
                              >> clinic. What existing
                              >>>> FOSS solutions are available?
                              >>>>
                              >>>> With best regards,
                              >>>>
                              >>>> [wr]
                              >>>>
                              >>>> - - - - - - - -
                              >>>>
                              >>>> will ross
                              >>>> chief information officer
                              >>>> mendocino health records exchange
                              >>>> 216 west perkins street, suite 206
                              >>>> ukiah, california 95482 usa
                              >>>> 707.462.6369 [office]
                              >>>> 707.462.5015 [fax]
                              >>>> www.mendocinohre.org
                              >>>>
                              >>>> - - - - - - - -
                              >>>>
                              >>>> "Getting people to adopt common standards is
                              >> impeded by patents."
                              >>>> Sir Tim Berners-Lee, BCS, 2006
                              >>>>
                              >>>> - - - - - - - -
                              >>>>
                              >>>>
                              >>>>
                              >>>
                              >>>
                              >>> [Non-text portions of this message have been
                              >> removed]
                              >>>
                              >>>
                              >>>
                              >>> ------------------------ Yahoo! Groups Sponsor
                              >> --------------------
                              >>> ~-->
                              >>> Yahoo! Groups gets a make over. See the new email
                              >> design.
                              >>>
                              >>
                              > http://us.click.yahoo.com/hOt0.A/lOaOAA/yQLSAA/W4wwlB/TM
                              >>>
                              >>
                              > --------------------------------------------------------------------
                              >>
                              >>> ~->
                              >>>
                              >>>
                              >>> Yahoo! Groups Links
                              >>>
                              >>>
                              >>>
                              >>>
                              >>
                              >> [wr]
                              >>
                              >> - - - - - - - -
                              >>
                              >> will ross
                              >> chief information officer
                              >> mendocino health records exchange
                              >> 216 west perkins street, suite 206
                              >> ukiah, california 95482 usa
                              >> 707.462.6369 [office]
                              >> 707.462.5015 [fax]
                              >> www.mendocinohre.org
                              >>
                              >> - - - - - - - -
                              >>
                              >> "Getting people to adopt common standards is impeded
                              >> by patents."
                              >> Sir Tim Berners-Lee, BCS, 2006
                              >>
                              >> - - - - - - - -
                              >>
                              >>
                              >>
                              >
                              >
                              >
                              >
                              > ______________________________________________________________________
                              > ______________
                              > The fish are biting.
                              > Get more visitors on your site using Yahoo! Search Marketing.
                              > http://searchmarketing.yahoo.com/arp/sponsoredsearch_v2.php
                              >
                              >
                              > ------------------------ Yahoo! Groups Sponsor --------------------
                              > ~-->
                              > Something is new at Yahoo! Groups. Check out the enhanced email
                              > design.
                              > http://us.click.yahoo.com/kOt0.A/gOaOAA/yQLSAA/W4wwlB/TM
                              > --------------------------------------------------------------------
                              > ~->
                              >
                              >
                              > Yahoo! Groups Links
                              >
                              >
                              >
                              >

                              [wr]

                              - - - - - - - -

                              will ross
                              chief information officer
                              mendocino health records exchange
                              216 west perkins street, suite 206
                              ukiah, california 95482 usa
                              707.462.6369 [office]
                              707.462.5015 [fax]
                              www.mendocinohre.org

                              - - - - - - - -

                              "Getting people to adopt common standards is impeded by patents."
                              Sir Tim Berners-Lee, BCS, 2006

                              - - - - - - - -
                            • madhusasidhar@netscape.net
                              You may find the patient de-identifcation features of this project interesting: http://www.mii.ucla.edu/index.php/MainSite:NLPHome ... From:
                              Message 14 of 19 , Mar 3, 2007
                              • 0 Attachment
                                You may find the patient de-identifcation features of this project interesting:
                                http://www.mii.ucla.edu/index.php/MainSite:NLPHome

                                -----Original Message-----
                                From: wross@...
                                To: openhealth@yahoogroups.com
                                Sent: Sat, 3 Mar 2007 11:31 AM
                                Subject: Re: [openhealth] Suppressing Sensitive Info From Free Text

                                Nandalal,

                                I believe you are exactly right. In the case of this interesting
                                problem the key issue is to identify the appropriate middleware
                                services to safely expose legacy patient data. This is a different
                                problem from the opportunity to create structured and coded data as
                                new systems with rich onboard permissions and are brought on line.

                                With best regards,

                                [wr]

                                - - - - - - - -

                                On Mar 3, 2007, at 2:02 AM, Nandalal Gunaratne wrote:

                                > Thanks Ross!
                                >
                                > Due to your question i have come to know the present
                                > state of text mining and NLP. These will give you your
                                > solution I guess.
                                >
                                > http://portal.acm.org/citation.cfm?
                                > id=1089824&dl=acm&coll=&CFID=15151515&CFTOKEN=6184618
                                >
                                > nandalal
                                > --- Will Ross <wross@...> wrote:
                                >
                                >> Dear 80n,
                                >>
                                >> This is, in fact, the use case in discussion.
                                >>
                                >> Assume the patient has agreed to suppress "detail x"
                                >> from circulation
                                >> beyond his/her physician's eyes in the local free
                                >> text based records
                                >> system. What are the best FOSS tools to publish to
                                >> the general
                                >> circulation records environment a correctly edited
                                >> version of a text
                                >> file?
                                >>
                                >> With best regards,
                                >>
                                >> [wr]
                                >>
                                >> - - - - - - - -
                                >>
                                >> On Mar 2, 2007, at 4:08 PM, 80n wrote:
                                >>
                                >>> Will
                                >>> The only acceptable answer would be Maury's option
                                >> 3. The patient
                                >>> decides.
                                >>> Anything else would be be inappropriate.
                                >>>
                                >>> And not just HIV status. The patient, and only
                                >> the patient, should
                                >>> have the
                                >>> right to determine who has access to anything that
                                >> the patient might
                                >>> consider sensitive. And only the patient can
                                >> determine what is or
                                >>> is not
                                >>> sensitive.
                                >>>
                                >>> 80n
                                >>>
                                >>>
                                >>>
                                >>> On 3/2/07, Will Ross <wross@...>
                                >> wrote:
                                >>>>
                                >>>> I'm looking for a tool to suppress sensitive
                                >> information (e.g., HIV
                                >>>> status, etc.) from free text clinical notes prior
                                >> to allowing the
                                >>>> notes to be published from a protected,
                                >> physician-only area into
                                >>>> general circulation patient records for the
                                >> clinic. What existing
                                >>>> FOSS solutions are available?
                                >>>>
                                >>>> With best regards,
                                >>>>
                                >>>> [wr]
                                >>>>
                                >>>> - - - - - - - -
                                >>>>
                                >>>> will ross
                                >>>> chief information officer
                                >>>> mendocino health records exchange
                                >>>> 216 west perkins street, suite 206
                                >>>> ukiah, california 95482 usa
                                >>>> 707.462.6369 [office]
                                >>>> 707.462.5015 [fax]
                                >>>> www.mendocinohre.org
                                >>>>
                                >>>> - - - - - - - -
                                >>>>
                                >>>> "Getting people to adopt common standards is
                                >> impeded by patents."
                                >>>> Sir Tim Berners-Lee, BCS, 2006
                                >>>>
                                >>>> - - - - - - - -
                                >>>>
                                >>>>
                                >>>>
                                >>>
                                >>>
                                >>> [Non-text portions of this message have been
                                >> removed]
                                >>>
                                >>>
                                >>>
                                >>> ------------------------ Yahoo! Groups Sponsor
                                >> --------------------
                                >>> ~-->
                                >>> Yahoo! Groups gets a make over. See the new email
                                >> design.
                                >>>
                                >>
                                > http://us.click.yahoo.com/hOt0.A/lOaOAA/yQLSAA/W4wwlB/TM
                                >>>
                                >>
                                > ----------------------------------------------------------
                                >>
                                >>> ~->
                                >>>
                                >>>
                                >>> Yahoo! Groups Links
                                >>>
                                >>>
                                >>>
                                >>>
                                >>
                                >> [wr]
                                >>
                                >> - - - - - - - -
                                >>
                                >> will ross
                                >> chief information officer
                                >> mendocino health records exchange
                                >> 216 west perkins street, suite 206
                                >> ukiah, california 95482 usa
                                >> 707.462.6369 [office]
                                >> 707.462.5015 [fax]
                                >> www.mendocinohre.org
                                >>
                                >> - - - - - - - -
                                >>
                                >> "Getting people to adopt common standards is impeded
                                >> by patents."
                                >> Sir Tim Berners-Lee, BCS, 2006
                                >>
                                >> - - - - - - - -
                                >>
                                >>
                                >>
                                >
                                >
                                >
                                >
                                > __________________________________________________________
                                > ______________
                                > The fish are biting.
                                > Get more visitors on your site using Yahoo! Search Marketing.
                                > http://searchmarketing.yahoo.com/arp/sponsoredsearch_v2.php
                                >
                                >
                                > ------------------------ Yahoo! Groups Sponsor --------------------
                                > ~-->
                                > Something is new at Yahoo! Groups. Check out the enhanced email
                                > design.
                                > http://us.click.yahoo.com/kOt0.A/gOaOAA/yQLSAA/W4wwlB/TM
                                > ----------------------------------------------------------
                                > ~->
                                >
                                >
                                > Yahoo! Groups Links
                                >
                                >
                                >
                                >

                                [wr]

                                - - - - - - - -

                                will ross
                                chief information officer
                                mendocino health records exchange
                                216 west perkins street, suite 206
                                ukiah, california 95482 usa
                                707.462.6369 [office]
                                707.462.5015 [fax]
                                www.mendocinohre.org

                                - - - - - - - -

                                "Getting people to adopt common standards is impeded by patents."
                                Sir Tim Berners-Lee, BCS, 2006

                                - - - - - - - -


                                ________________________________________________________________________
                                Check Out the new free AIM(R) Mail -- 2 GB of storage and industry-leading spam and email virus protection.


                                [Non-text portions of this message have been removed]
                              • JohnLeo Zimmer, MD
                                ... Will, Could you give a little more information on the structure of such a clinic? I am not aware of any practices with a protected, physician-only area
                                Message 15 of 19 , Mar 4, 2007
                                • 0 Attachment
                                  Will Ross wrote:
                                  > I'm looking for a tool to suppress sensitive information (e.g., HIV
                                  > status, etc.) from free text clinical notes prior to allowing the
                                  > notes to be published from a protected, physician-only area
                                  > into general circulation patient records for the clinic.

                                  Will,
                                  Could you give a little more information on the structure of such a
                                  clinic? I am not aware of any practices with a "protected,
                                  physician-only area" more sheltered than "general circulation".

                                  Once I produce my part of a record it is available to other physicians,
                                  nurses, scheduling and billing folk. Confidentiality requires the whole
                                  team to protect sensitive information.

                                  How will a "general circulation patient record" be used?

                                  Further:
                                  There are difficulties far beyond the obvious risk of something slipping
                                  through in free text.

                                  Take the HIV example:
                                  A medication list could contain medications used only for HIV. (Likewise
                                  an allergy list referring to any such a medication.) Diagnoses that
                                  herald underlying HIV infection would have to be caught. Likewise
                                  laboratory testing, such as CD4 counts, X-ray diagnoses, pathology
                                  reports. Specialty clinics that a patient may be referred to (and
                                  references to any reports <from> such sources).

                                  Unless the record is very impoverished to begin with, it will probably
                                  be leaky by its very nature. Effort might be better spent at educating
                                  the entire staff on their ethical responsibilities.

                                  Technology could be useful for detecting inappropriate patterns of use.

                                  jlz
                                • Will Ross
                                  John, In this use case, the record is not held by the health care site where the patient s confidential information is secure and private, but in a community
                                  Message 16 of 19 , Mar 4, 2007
                                  • 0 Attachment
                                    John,

                                    In this use case, the record is not held by the health care site
                                    where the patient's confidential information is secure and private,
                                    but in a community repository operated by a Regional Health
                                    Information Organization (RHIO). Operating edge proxies which host
                                    access to uploaded copies of patient records, the RHIO seeks an
                                    appropriate compromise between routine access to patient health data
                                    and protection of sensitive information. Unfortunately, the
                                    originating records combine both routine and sensitive patient
                                    information in a monolithic free text format, hence the search for an
                                    appropriate NLP scrubbing step prior to export.

                                    Did I answer your question?

                                    With best regards,

                                    [wr]

                                    - - - - - - - -

                                    On Mar 4, 2007, at 1:01 PM, JohnLeo Zimmer, MD wrote:

                                    > Will Ross wrote:
                                    >> I'm looking for a tool to suppress sensitive information (e.g., HIV
                                    >> status, etc.) from free text clinical notes prior to allowing the
                                    >> notes to be published from a protected, physician-only area
                                    >> into general circulation patient records for the clinic.
                                    >
                                    > Will,
                                    > Could you give a little more information on the structure of such a
                                    > clinic? I am not aware of any practices with a "protected,
                                    > physician-only area" more sheltered than "general circulation".
                                    >
                                    > Once I produce my part of a record it is available to other
                                    > physicians,
                                    > nurses, scheduling and billing folk. Confidentiality requires the
                                    > whole
                                    > team to protect sensitive information.
                                    >
                                    > How will a "general circulation patient record" be used?
                                    >
                                    > Further:
                                    > There are difficulties far beyond the obvious risk of something
                                    > slipping
                                    > through in free text.
                                    >
                                    > Take the HIV example:
                                    > A medication list could contain medications used only for HIV.
                                    > (Likewise
                                    > an allergy list referring to any such a medication.) Diagnoses that
                                    > herald underlying HIV infection would have to be caught. Likewise
                                    > laboratory testing, such as CD4 counts, X-ray diagnoses, pathology
                                    > reports. Specialty clinics that a patient may be referred to (and
                                    > references to any reports <from> such sources).
                                    >
                                    > Unless the record is very impoverished to begin with, it will probably
                                    > be leaky by its very nature. Effort might be better spent at educating
                                    > the entire staff on their ethical responsibilities.
                                    >
                                    > Technology could be useful for detecting inappropriate patterns of
                                    > use.
                                    >
                                    > jlz
                                    >
                                    >
                                    >
                                    > ------------------------ Yahoo! Groups Sponsor --------------------
                                    > ~-->
                                    > Yahoo! Groups gets a make over. See the new email design.
                                    > http://us.click.yahoo.com/hOt0.A/lOaOAA/yQLSAA/W4wwlB/TM
                                    > --------------------------------------------------------------------
                                    > ~->
                                    >
                                    >
                                    > Yahoo! Groups Links
                                    >
                                    >
                                    >
                                    >

                                    [wr]

                                    - - - - - - - -

                                    will ross
                                    chief information officer
                                    mendocino health records exchange
                                    216 west perkins street, suite 206
                                    ukiah, california 95482 usa
                                    707.462.6369 [office]
                                    707.462.5015 [fax]
                                    www.mendocinohre.org

                                    - - - - - - - -

                                    "Getting people to adopt common standards is impeded by patents."
                                    Sir Tim Berners-Lee, BCS, 2006

                                    - - - - - - - -
                                  • JohnLeo Zimmer, MD
                                    ... Thank you for your response, Will. I fear I am being intentionally obtuse. But I get stuck at this distinction between routine access and sensitive
                                    Message 17 of 19 , Mar 4, 2007
                                    • 0 Attachment
                                      Will Ross wrote:
                                      > John,
                                      >
                                      > In this use case, the record is not held by the health care site
                                      > where the patient's confidential information is secure and private,
                                      > but in a community repository operated by a Regional Health
                                      > Information Organization (RHIO). Operating edge proxies which host
                                      > access to uploaded copies of patient records, the RHIO seeks an
                                      > appropriate compromise between routine access to patient health data
                                      > and protection of sensitive information. Unfortunately, the
                                      > originating records combine both routine and sensitive patient
                                      > information in a monolithic free text format, hence the search for an
                                      > appropriate NLP scrubbing step prior to export.
                                      >
                                      > Did I answer your question?
                                      >

                                      Thank you for your response, Will.

                                      I fear I am being intentionally obtuse. But I get stuck at this
                                      distinction between routine access and sensitive information. Perhaps
                                      the RHIO gets to define the distinction? I think others have pointed out
                                      that one person may consider information sensitive that another may
                                      regard as routine, or even public.

                                      I will withdraw to learn more about the RHIO. :-)

                                      regards,
                                      JohnLeoZ
                                    • Tim Cook
                                      Will, ... I believe what John is trying to explain is that ALL patient health information (PHI) is considered sensitive. Only the patient can determine which
                                      Message 18 of 19 , Mar 5, 2007
                                      • 0 Attachment
                                        Will,

                                        Will Ross wrote:
                                        > In this use case, the record is not held by the health care site
                                        > where the patient's confidential information is secure and private,
                                        > but in a community repository operated by a Regional Health
                                        > Information Organization (RHIO). Operating edge proxies which host
                                        > access to uploaded copies of patient records, the RHIO seeks an
                                        > appropriate compromise between routine access to patient health data
                                        > and protection of sensitive information.

                                        I believe what John is trying to explain is that ALL patient health
                                        information (PHI) is considered sensitive. Only the patient can
                                        determine which bits of information should be released to outside
                                        entities.

                                        Do all the members of the RHIO have HIPPA Business Associate
                                        Agreements? http://www.uthscsa.edu/hipaa/assoc-contract.html The
                                        types and uses of the PHI should already be defined in those.

                                        Therefore the RHIO should not be receiving any information from the
                                        originating sources that hasn't already been released by the patient.

                                        Please Note: I am not a lawyer nor even a HIPPA expert so part of this
                                        explanation may be incorrect. I have however read the guidelines and
                                        believe my understanding to be accurate.

                                        > Unfortunately, the
                                        > originating records combine both routine and sensitive patient
                                        > information in a monolithic free text format, hence the search for an
                                        > appropriate NLP scrubbing step prior to export.

                                        I think this is the appropriate place to note that this is your
                                        trade-off for "good enough" EMR systems vs. "well designed" EMR
                                        systems. It kind of reminds me of the Fram oil filter commercial
                                        (circa. 1974?) where the mechanic says "pay me now or pay me later".

                                        Cheers,
                                        Tim
                                      • John Norris
                                        In case you can t find anything, there are some tools to help you roll your own find-and-replace. I understand that may not get to removing certain semantics.
                                        Message 19 of 19 , Mar 5, 2007
                                        • 0 Attachment
                                          In case you can't find anything, there are some tools to help you roll
                                          your own find-and-replace. I understand that may not get to removing
                                          certain semantics.

                                          OpenMedSpel medical spelling word list:
                                          http://www.e-medtools.com/openmedspel.html
                                          (recently mentioned on LinuxMedNews)

                                          Consumer Health Vocabulary Initiative (Open Source):
                                          "Consumer health vocabularies link everyday words and phrases about
                                          health ("heart attack") to technical terms or jargon used by health
                                          care professionals ("myocardial infarction")."
                                          http://www.consumerhealthvocab.org/


                                          And this bit of hopeful news:

                                          In their own words? A terminological analysis of e-mail to a cancer
                                          information service.
                                          Smith CA, Stavri PZ, Chapman WW.

                                          "CONCLUSION: 96% of the clinical findings and features mentioned in
                                          e-mail by correspondents who did not self-identify as healthcare
                                          professionals were described using terms from controlled healthcare
                                          terminologies."

                                          http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?CMD=search&DB=pubmed

                                          Hope that is helpful in some way.

                                          John
                                          (Currently writing a paper for my Informatics class on a similar theme
                                          and had those refs handy.)


                                          --
                                          http://john-norris.net
                                        Your message has been successfully submitted and would be delivered to recipients shortly.